23 accepted papers
Reinforcement learning (RL), particularly RL from verifiable reward (RLVR), has become a crucial phase of training large language models (LLMs) and a key focus of current scaling efforts. However, optimization practices in RL largely follow those of next-token-prediction stages (e.g., pretraining an…
The LLM-as-a-judge paradigm is widely used in both evaluating free-text model responses and reward modeling for model alignment and finetuning. Recently, finetuning judges with judge-specific data has emerged as an often preferred choice over directly prompting frontier models as judges, as the form…
Conversational agents powered by large language models (LLMs) with tool integration achieve strong performance on fixed task-oriented dialogue datasets but remain vulnerable to unanticipated, user-induced errors. Rather than focusing on error prevention, this work focuses on error recovery, which ne…
Large Language Models (LLMs) with API-calling capabilities enabled building effective Language Agents (LA), while also revolutionizing the conventional task-oriented dialogue (TOD) paradigm. However, current approaches face a critical dilemma: TOD systems are often trained on a limited set of target…
As chatbots continue to evolve toward human-like, real-world, interactions, multimodality remains an active area of research and exploration. So far, efforts to integrate multimodality into chatbots have primarily focused on image-centric tasks, such as visual dialogue and image-based instructions,…
Despite seemingly performant web agents on the task-completion benchmarks, most existing methods evaluate the agents based on a presupposition: the web navigation task consists of a linear sequence of actions with an end state that marks task completion. In contrast, our work focuses on web navigati…
Recent LLMs have enabled significant advancements for conversational agents. However, they are also well known to hallucinate, producing responses that seem plausible but are factually incorrect. On the other hand, users tend to over-rely on LLM-based AI agents, accepting AI’s suggestion even when i…
We introduce MIRAGE, a new benchmark for multimodal expert-level reasoning and decision-making in consultative interaction settings. Designed for the domain of agriculture, MIRAGE captures the full complexity of expert consultations by combining natural user queries, expert-authored responses, and i…
Influence functions provide crucial insights into model training, but existing methods suffer from large computational costs and limited generalization. Particularly, recent works have proposed various metrics and algorithms to calculate the influence of data using language models, which do not scal…
Reinforcement learning (RL) yields substantial improvements in large language models’ (LLMs) downstream task performance and alignment with human values. Surprisingly, such large gains result from updating only a small subnetwork comprising just 5%-30% of the parameters, with the rest effectively un…
Current Large Language Model (LLM) agents demonstrate strong reasoning and tool use capabilities, but often lack self-awareness, failing to balance these approaches effectively. This imbalance leads to **Tool Overuse**, where models unnecessarily rely on external tools for tasks solvable with parame…
Current Large Language Models (LLMs) often undergo supervised fine-tuning (SFT) to acquire tool use capabilities. However, SFT struggles to generalize to unfamiliar or complex tool use scenarios. Recent advancements in reinforcement learning (RL), particularly with R1-like models, have demonstrated…
Conversational, multi-turn, text-to-SQL (CoSQL) tasks map natural language utterances in a dialogue to SQL queries. State-of-the-art (SOTA) systems use large, pre-trained and finetuned language models, such as the T5-family, in conjunction with constrained decoding. With multi-tasking (MT) over cohe…
Human interlocutors adapt their behavior to each other in a conversation through entrainment. While entrainment has been found in long chit-chat conversations, much less research has been conducted on task-oriented dialogs. In this paper, we investigate short task-oriented Wizard-of-Oz conversations…
Dot-product attention is a core module in the present generation of neural network models, particularly transformers, and is being leveraged across numerous areas such as natural language processing and computer vision. This attention module is comprised of three linear transformations, namely query…
Controlling neural network-based models for natural language generation (NLG) to realize desirable attributes in the generated outputs has broad applications in numerous areas such as machine translation, document summarization, and dialog systems. Approaches that enable such control in a zero-shot…
Different flavors of transfer learning have shown tremendous impact in advancing research and applications of machine learning. In this work we study the use of a certain family of transfer learning, where the target domain is mapped to the source domain. Specifically we map Natural Language Underst…
Spoken language understanding (SLU) is a component of goal-oriented dialogue systems that aims to interpret user's natural language queries in system's semantic representation format. While current state-of-the-art SLU approaches achieve high performance for English domains, the same is not true for…
Natural language understanding and dialogue policy learning are both essential in conversational systems that predict the next system actions in response to a current user utterance. Conventional approaches aggregate separate models of natural language understanding (NLU) and system action predictio…
Spoken dialogue systems must be able to recover gracefully from unexpected user inputs. In many cases, these unexpected utterances may be within the scope of the system, but include previously unseen phrases that the system cannot interpret. In this work, we augment a spoken dialogue system with the…
The recent surge of intelligent personal assistants motivates spoken language understanding of dialogue systems. However, the domain constraint along with the inflexible intent schema remains a big issue. This paper focuses on the task of intent expansion, which helps remove the domain limit and mak…
While ensemble models have proven useful for sequence learning tasks there is relatively fewer work that provide insights into what makes them powerful. In this paper, we investigate the empirical behavior of the ensemble approaches on sequence modeling, specifically for the semantic tagging task. W…
Many users obtain content from a screen and want to make requests of a system based on items that they have seen. Eye-gaze information is a valuable signal in speech recognition and spoken-language understanding (SLU) because it provides context for a user's next utterance-what the user says next is…